Prompting for products: investigating design space exploration strategies for text-to-image generative models
Text-to-image models are enabling efficient design space exploration, rapidly generating images from text prompts. However, many generative AI tools are imperfect for product design applications as they are not built for the goals and requirements of product design. The unclear link between text inp...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2025-01-01
|
| Series: | Design Science |
| Subjects: | |
| Online Access: | https://www.cambridge.org/core/product/identifier/S2053470124000519/type/journal_article |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526429931536384 |
|---|---|
| author | Leah Chong I-Ping Lo Jude Rayan Steven Dow Faez Ahmed Ioanna Lykourentzou |
| author_facet | Leah Chong I-Ping Lo Jude Rayan Steven Dow Faez Ahmed Ioanna Lykourentzou |
| author_sort | Leah Chong |
| collection | DOAJ |
| description | Text-to-image models are enabling efficient design space exploration, rapidly generating images from text prompts. However, many generative AI tools are imperfect for product design applications as they are not built for the goals and requirements of product design. The unclear link between text input and image output further complicates their application. This work empirically investigates design space exploration strategies that can successfully yield product images that are feasible, novel and aesthetic – three common goals in product design. Specifically, users’ actions within the global and local editing modes, including their time spent, prompt length, mono versus multi-criteria prompts, and goal orientation of prompts, are analyzed. Key findings reveal the pivotal role of mono versus multi-criteria and goal orientation of prompts in achieving specific design goals over time and prompt length. The study recommends prioritizing the use of multi-criteria prompts for feasibility and novelty during global editing while favoring mono-criteria prompts for aesthetics during local editing. Overall, this article underscores the nuanced relationship between the AI-driven text-to-image models and their effectiveness in product design, urging designers to carefully structure prompts during different editing modes to better meet the unique demands of product design. |
| format | Article |
| id | doaj-art-7894b81d669d408f922ff320144d7001 |
| institution | Kabale University |
| issn | 2053-4701 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Design Science |
| spelling | doaj-art-7894b81d669d408f922ff320144d70012025-01-16T21:49:14ZengCambridge University PressDesign Science2053-47012025-01-011110.1017/dsj.2024.51Prompting for products: investigating design space exploration strategies for text-to-image generative modelsLeah Chong0I-Ping Lo1Jude Rayan2Steven Dow3Faez Ahmed4https://orcid.org/0000-0002-5227-2628Ioanna Lykourentzou5https://orcid.org/0000-0002-4243-4128Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USADepartment of Information and Computing Sciences, Utrecht University, Utrecht, NetherlandsDepartment of Cognitive Science, University of California, San Diego, San Diego, CA, USADepartment of Cognitive Science, University of California, San Diego, San Diego, CA, USADepartment of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USADepartment of Information and Computing Sciences, Utrecht University, Utrecht, NetherlandsText-to-image models are enabling efficient design space exploration, rapidly generating images from text prompts. However, many generative AI tools are imperfect for product design applications as they are not built for the goals and requirements of product design. The unclear link between text input and image output further complicates their application. This work empirically investigates design space exploration strategies that can successfully yield product images that are feasible, novel and aesthetic – three common goals in product design. Specifically, users’ actions within the global and local editing modes, including their time spent, prompt length, mono versus multi-criteria prompts, and goal orientation of prompts, are analyzed. Key findings reveal the pivotal role of mono versus multi-criteria and goal orientation of prompts in achieving specific design goals over time and prompt length. The study recommends prioritizing the use of multi-criteria prompts for feasibility and novelty during global editing while favoring mono-criteria prompts for aesthetics during local editing. Overall, this article underscores the nuanced relationship between the AI-driven text-to-image models and their effectiveness in product design, urging designers to carefully structure prompts during different editing modes to better meet the unique demands of product design.https://www.cambridge.org/core/product/identifier/S2053470124000519/type/journal_articledesign space explorationproduct designprompt engineeringtext-to-image generative AI |
| spellingShingle | Leah Chong I-Ping Lo Jude Rayan Steven Dow Faez Ahmed Ioanna Lykourentzou Prompting for products: investigating design space exploration strategies for text-to-image generative models Design Science design space exploration product design prompt engineering text-to-image generative AI |
| title | Prompting for products: investigating design space exploration strategies for text-to-image generative models |
| title_full | Prompting for products: investigating design space exploration strategies for text-to-image generative models |
| title_fullStr | Prompting for products: investigating design space exploration strategies for text-to-image generative models |
| title_full_unstemmed | Prompting for products: investigating design space exploration strategies for text-to-image generative models |
| title_short | Prompting for products: investigating design space exploration strategies for text-to-image generative models |
| title_sort | prompting for products investigating design space exploration strategies for text to image generative models |
| topic | design space exploration product design prompt engineering text-to-image generative AI |
| url | https://www.cambridge.org/core/product/identifier/S2053470124000519/type/journal_article |
| work_keys_str_mv | AT leahchong promptingforproductsinvestigatingdesignspaceexplorationstrategiesfortexttoimagegenerativemodels AT ipinglo promptingforproductsinvestigatingdesignspaceexplorationstrategiesfortexttoimagegenerativemodels AT juderayan promptingforproductsinvestigatingdesignspaceexplorationstrategiesfortexttoimagegenerativemodels AT stevendow promptingforproductsinvestigatingdesignspaceexplorationstrategiesfortexttoimagegenerativemodels AT faezahmed promptingforproductsinvestigatingdesignspaceexplorationstrategiesfortexttoimagegenerativemodels AT ioannalykourentzou promptingforproductsinvestigatingdesignspaceexplorationstrategiesfortexttoimagegenerativemodels |